Watson Tone Analyzer : #IBM
A cognitive computing experiment to analyze an audience's collective tone of voice
In this fun cognitive computing experiment, Watson is analyzing the tone of voice of your collective tweets.#IBM 'n' see pin change color!
IBM Watson Tone Analyzer helps us analyze email messages, presentations, tweets, and other communications before sending them out. It examines how others might perceive our tone in written messages and helps us understand the potential impact of our words. To try out the Tone Analyzer yourself and to view other Cognitive Computing services, click here.
An Arduino compatible microcontroller with WiFi capability and a RGB LED shield display the aggregated statistics. The NeoPixel ring is connected to Watson IoT Platform, receiving updated stats each minute. The 24 LEDs, illuminated with a tiny Lithium Polymer battery mounted on the back, change colors to represent the tone of the tweets.
The IBM Watson Tone Analyzer Service uses linguistic analysis to detect three types of tones from written text: Emotions, Social Tendencies, and Writing Style. In this demo, we use identified social tones that infer the personality of the individual reflected in tweets around a search query.
Tone Analyzer currently infers five different social tones: Openness, Conscientiousness, Extraversion, Agreeableness, and Emotional Range (alternatively Neuroticism). These five social tones are adopted from the Big-five personality model.
Each tweet is analyzed individually and categorized with the tone that ranks highest. The tweet is then aggregated together with others that share the same tone.
Node-RED provides a browser-based flow editor that makes it easy to wire together flows using the wide range nodes in the palette. Flows can be then deployed to the runtime in a single-click. Using IBM Watson's Tone Analyzer, tweets are processed for prominent tone and aggregated every minute.